SAM 2++: Tracking Anything at Any Granularity | Paper Citation Record

Observation 63383ab6-7193-4975-9ee2-c90fef11fe09 · outbound

This paper cites Burst: A benchmark for unifying object recognition, segmentation and tracking in video.

SAM 2++: Tracking Anything at Any Granularity Burst: A benchmark for unifying object recognition, segmentation and tracking in video

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.683838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7dbe3399-90f6-4f35-92cf-b900bd632dbb · outbound

This paper cites Track-on: Transformer-based online point tracking with memory.

SAM 2++: Tracking Anything at Any Granularity Track-on: Transformer-based online point tracking with memory

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.674805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9a353a24-761b-487e-8412-c1079ac22a4f · outbound

This paper cites Ar- trackv2: Prompting autoregressive tracker where to look and how to describe.

SAM 2++: Tracking Anything at Any Granularity Ar- trackv2: Prompting autoregressive tracker where to look and how to describe

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.620936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 83593d67-916a-46f5-bb42-c070fce7d525 · outbound

This paper cites A benchmark and simulator for uav track- ing.

SAM 2++: Tracking Anything at Any Granularity A benchmark and simulator for uav track- ing

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.610414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 744b213e-cfd2-44c9-a8e3-f30b3ad4b9da · outbound

This paper cites Creatures great and SMAL: Recovering the shape and motion of animals from video.

SAM 2++: Tracking Anything at Any Granularity Creatures great and SMAL: Recovering the shape and motion of animals from video

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.587074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 55dc52c5-75c5-4924-80d1-299ae098c5d0 · outbound

This paper cites Hiptrack: Visual tracking with historical prompts.

SAM 2++: Tracking Anything at Any Granularity Hiptrack: Visual tracking with historical prompts

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.584653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b50aa775-146c-4955-88ce-ae1b53c0d5be · outbound

This paper cites Ro- bust object modeling for visual tracking.

SAM 2++: Tracking Anything at Any Granularity Ro- bust object modeling for visual tracking

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.579591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ba5068a3-5aaf-420b-90f0-38c5ea1dae20 · outbound

This paper cites Pix2seq: A Language Modeling Framework for Object Detection.

SAM 2++: Tracking Anything at Any Granularity Pix2seq: A Language Modeling Framework for Object Detection

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-21T19:54:20.148463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0459c716-ea05-4039-9d22-2240dafa4ea2 · outbound

This paper cites Sam-adapter: Adapting segment anything in underperformed scenes.

SAM 2++: Tracking Anything at Any Granularity Sam-adapter: Adapting segment anything in underperformed scenes

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.546023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 400d7e1e-ae9b-451c-b2b8-6607bf334746 · outbound

This paper cites Seqtrack: Sequence to sequence learning for visual ob- ject tracking.

SAM 2++: Tracking Anything at Any Granularity Seqtrack: Sequence to sequence learning for visual ob- ject tracking

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.574298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8b99bfe-2b87-49a8-8732-a3ff9e8c9296 · outbound

This paper cites an unresolved cited work.

SAM 2++: Tracking Anything at Any Granularity Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-21T19:54:20.703631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7319a147-ce57-4071-b2f9-d2e6049143b0 · outbound

This paper cites Rethink- ing space-time networks with improved memory coverage for efficient video object segmentation.

SAM 2++: Tracking Anything at Any Granularity Rethink- ing space-time networks with improved memory coverage for efficient video object segmentation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.701333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fc6ada56-51a9-4dda-93c8-ccc26d64a656 · outbound

This paper cites Price, Alexan- der G.

SAM 2++: Tracking Anything at Any Granularity Price, Alexan- der G

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.697209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 653a906d-2757-4944-9292-35d1325d7093 · outbound

This paper cites Price, Joon-Young Lee, and Alexander G.

SAM 2++: Tracking Anything at Any Granularity Price, Joon-Young Lee, and Alexander G

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.699154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9146752e-ef12-421b-a5be-aaa3818a6fc8 · outbound

This paper cites Local all-pair corre- spondence for point tracking.

SAM 2++: Tracking Anything at Any Granularity Local all-pair corre- spondence for point tracking

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.624638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 86f11d04-f0e9-47b8-b8c0-b98b22d5c2c2 · outbound

This paper cites Mixformer: End-to-end tracking with iterative mixed atten- tion.IEEE Transactions on Pattern Analysis and Machine Intelligence.

SAM 2++: Tracking Anything at Any Granularity Mixformer: End-to-end tracking with iterative mixed atten- tion.IEEE Transactions on Pattern Analysis and Machine Intelligence

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.695058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 28041687-0920-4048-89f8-e50b8c276934 · outbound

This paper cites Samwise: Infusing wisdom in sam2 for text-driven video segmentation.

SAM 2++: Tracking Anything at Any Granularity Samwise: Infusing wisdom in sam2 for text-driven video segmentation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.693034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bc5f1c8d-622c-4b6a-a1e1-c69db2da2b15 · outbound

This paper cites Epic-kitchens visor benchmark: Video segmenta- tions and object relations.

SAM 2++: Tracking Anything at Any Granularity Epic-kitchens visor benchmark: Video segmenta- tions and object relations

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.607144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ec3375f7-77fa-4fc7-acfa-613acc82a87b · outbound

This paper cites Torr, and Song Bai.

SAM 2++: Tracking Anything at Any Granularity Torr, and Song Bai

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.688835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6423bdad-c76d-4025-99dd-f4cdae60ba47 · outbound

This paper cites SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree.

SAM 2++: Tracking Anything at Any Granularity SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-21T19:54:20.140269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 34163935-1a08-49ca-aa64-cf2ee66e93bc · outbound

This paper cites TAP-vid: A benchmark for track- ing any point in a video.Advances in Neural Information Processing Systems, 35:13610–13626.

SAM 2++: Tracking Anything at Any Granularity TAP-vid: A benchmark for track- ing any point in a video.Advances in Neural Information Processing Systems, 35:13610–13626

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.687086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7365a913-bbac-4d76-bdf6-3ce3cada0346 · outbound

This paper cites Tapir: Tracking any point with per-frame initialization and temporal refinement.

SAM 2++: Tracking Anything at Any Granularity Tapir: Tracking any point with per-frame initialization and temporal refinement

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.603819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0d8a83cc-c4bd-4e76-b5b8-f8d382447193 · outbound

This paper cites Lasot: A high-quality benchmark for large-scale single ob- ject tracking.

SAM 2++: Tracking Anything at Any Granularity Lasot: A high-quality benchmark for large-scale single ob- ject tracking

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.594731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d2f67da4-7af9-4436-b8b2-e118dae40913 · outbound

This paper cites Generalized relation modeling for transformer tracking.

SAM 2++: Tracking Anything at Any Granularity Generalized relation modeling for transformer tracking

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.680597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 265c0c1c-215a-4b89-a522-aa8084d3ff7a · outbound

This paper cites Learn- ing to linearize under uncertainty.Advances in neural infor- mation processing systems, 28.

SAM 2++: Tracking Anything at Any Granularity Learn- ing to linearize under uncertainty.Advances in neural infor- mation processing systems, 28

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.678497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 64580acf-3d6c-4701-8e33-bb5b84fbeaa0 · outbound

This paper cites Tag: Tracking at any granularity.

SAM 2++: Tracking Anything at Any Granularity Tag: Tracking at any granularity

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.672282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9b44bb96-eec4-4b51-ac06-d27992b79df0 · outbound

This paper cites Particle video revisited: Tracking through occlusions using point trajectories.

SAM 2++: Tracking Anything at Any Granularity Particle video revisited: Tracking through occlusions using point trajectories

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.706252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c51930dc-3c25-4144-b0e8-33c18ba09a61 · outbound

This paper cites Lvos: A benchmark for long-term video object segmentation.

SAM 2++: Tracking Anything at Any Granularity Lvos: A benchmark for long-term video object segmentation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.703864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 053fba8b-5e7d-4133-90bc-aa78cef1a9cd · outbound

This paper cites LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation.

SAM 2++: Tracking Anything at Any Granularity LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-21T19:54:20.145714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 11037b95-2948-41b5-8941-4c5e4bc2c70a · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen.

SAM 2++: Tracking Anything at Any Granularity Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.698797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d8077ce2-7316-49d9-8dbc-04af1177658a · outbound

This paper cites Got-10k: A large high-diversity benchmark for generic object tracking in the wild.IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 43(5):1562–1577.

SAM 2++: Tracking Anything at Any Granularity Got-10k: A large high-diversity benchmark for generic object tracking in the wild.IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 43(5):1562–1577

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.696288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 676295a9-931c-48a1-b5aa-6897b80fe449 · outbound

This paper cites Unleashing the temporal-spatial reasoning capacity of gpt for training-free audio and language referenced video object segmentation.

SAM 2++: Tracking Anything at Any Granularity Unleashing the temporal-spatial reasoning capacity of gpt for training-free audio and language referenced video object segmentation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.693883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 36f82099-508f-490a-8e1e-0a3772c34cf9 · outbound

This paper cites CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos.

SAM 2++: Tracking Anything at Any Granularity CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-21T19:54:20.148960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3fbf6bb1-5aae-4c5d-90ab-5e435579fba1 · outbound

This paper cites Co- tracker: It is better to track together.

SAM 2++: Tracking Anything at Any Granularity Co- tracker: It is better to track together

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.691290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 72706f3e-244e-4d91-87aa-94e410f0efc6 · outbound

This paper cites Segment anything in high quality.

SAM 2++: Tracking Anything at Any Granularity Segment anything in high quality

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.688519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8d2b087e-4c3e-466f-b8ca-45dd768911d8 · outbound

This paper cites Need for speed: A benchmark for higher frame rate object tracking.

SAM 2++: Tracking Anything at Any Granularity Need for speed: A benchmark for higher frame rate object tracking

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.686098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9783b1d3-084e-407d-bd05-94a65704895b · outbound

This paper cites Segment Anything.

SAM 2++: Tracking Anything at Any Granularity Segment Anything

Reference 37

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T19:54:20.145594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1c845169-eded-425e-9655-965ce5f0cbdd · outbound

This paper cites TAPTR: tracking any point with transformers as detection.

SAM 2++: Tracking Anything at Any Granularity TAPTR: tracking any point with transformers as detection

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.701193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 833bfca4-60b0-436b-a816-7f530b71df0b · outbound

This paper cites Onevos: unifying video object segmentation with all-in-one transformer framework.

SAM 2++: Tracking Anything at Any Granularity Onevos: unifying video object segmentation with all-in-one transformer framework

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.681636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 777a5256-b58b-432f-bac9-0866f0c63875 · outbound

This paper cites Tracking meets lora: Faster training, larger model, stronger performance.

SAM 2++: Tracking Anything at Any Granularity Tracking meets lora: Faster training, larger model, stronger performance

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.679497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 274e6fd4-07dc-4ce3-8f6b-0294a96fcc9c · outbound

This paper cites Microsoft coco: Common objects in context.

SAM 2++: Tracking Anything at Any Granularity Microsoft coco: Common objects in context

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.677252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 417dc647-cd1d-45f9-bfca-c27d7128e693 · outbound

This paper cites SAMRefiner: Taming segment anything model for universal mask refine- ment.

SAM 2++: Tracking Anything at Any Granularity SAMRefiner: Taming segment anything model for universal mask refine- ment

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.629602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1e4ac733-60d9-424e-8f06-070afab4d81c · outbound

This paper cites Hota: A higher order metric for evaluating multi-object tracking.International Journal of Computer Vision, pages 1–31.

SAM 2++: Tracking Anything at Any Granularity Hota: A higher order metric for evaluating multi-object tracking.International Journal of Computer Vision, pages 1–31

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.670031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2dcd8944-ede5-48bf-8b91-dce94ddef649 · outbound

This paper cites Trackingnet: A large-scale dataset and benchmark for object tracking in the wild.

SAM 2++: Tracking Anything at Any Granularity Trackingnet: A large-scale dataset and benchmark for object tracking in the wild

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.667395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d35aceb-3493-4359-9f3c-e34afd61ec02 · outbound

This paper cites Simtrack: A simulation- based framework for scalable real-time object pose detection and tracking.

SAM 2++: Tracking Anything at Any Granularity Simtrack: A simulation- based framework for scalable real-time object pose detection and tracking

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.665004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dc9e0de3-4f0e-4389-b93a-bc457c10cd29 · outbound

This paper cites Vast- track: Vast category visual object tracking.

SAM 2++: Tracking Anything at Any Granularity Vast- track: Vast category visual object tracking

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.642886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8d492cc0-3185-4234-80fd-638aea4d1c1d · outbound

This paper cites A benchmark dataset and evaluation methodology for video 10 object segmentation.

SAM 2++: Tracking Anything at Any Granularity A benchmark dataset and evaluation methodology for video 10 object segmentation

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.662553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4856dc3d-b1c8-4791-97c1-0ad3dac826eb · outbound

This paper cites The 2017 DAVIS Challenge on Video Object Segmentation.

SAM 2++: Tracking Anything at Any Granularity The 2017 DAVIS Challenge on Video Object Segmentation

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-21T19:54:20.128421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9661f436-0137-4440-8129-ce128c0ce289 · outbound

This paper cites Perception test: A diagnostic benchmark for multimodal video models.

SAM 2++: Tracking Anything at Any Granularity Perception test: A diagnostic benchmark for multimodal video models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.659615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 86963e50-b20e-4ea1-b090-21a76739d9ea · outbound

This paper cites SAM 2: Segment Anything in Images and Videos.

SAM 2++: Tracking Anything at Any Granularity SAM 2: Segment Anything in Images and Videos

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-21T19:54:20.143105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4ede75d3-6ed0-4eca-abb7-696e2b6de7cf · outbound

This paper cites Breaking the “object” in video object segmentation.

SAM 2++: Tracking Anything at Any Granularity Breaking the “object” in video object segmentation

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.657009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6d6a4af8-8aac-4640-8f93-3c9fb1324511 · outbound

This paper cites A Distractor-Aware Memory for Visual Object Tracking with SAM2.

SAM 2++: Tracking Anything at Any Granularity A Distractor-Aware Memory for Visual Object Tracking with SAM2

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-21T19:54:20.129398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2cc5bd2a-4cdf-44db-8b6f-56da29a0e2b2 · outbound

This paper cites Omnitracker: Unifying visual object tracking by tracking-with-detection.

SAM 2++: Tracking Anything at Any Granularity Omnitracker: Unifying visual object tracking by tracking-with-detection

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.654546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a6a17176-15bf-4f15-b62c-5ceac1042561 · outbound

This paper cites Towards more flexible and accurate object tracking with natural language: Algo- rithms and benchmark.

SAM 2++: Tracking Anything at Any Granularity Towards more flexible and accurate object tracking with natural language: Algo- rithms and benchmark

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.655541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6fae17f4-3a57-4032-9bf3-e11b55b9a6de · outbound

This paper cites Do different track- ing tasks require different appearance models?Advances in neural information processing systems, 34:726–738.

SAM 2++: Tracking Anything at Any Granularity Do different track- ing tasks require different appearance models?Advances in neural information processing systems, 34:726–738

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.668593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4a3ea255-d323-4d18-9b4e-ca5f900c091a · outbound

This paper cites Autoregressive visual tracking.

SAM 2++: Tracking Anything at Any Granularity Autoregressive visual tracking

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.647242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 65deb6da-baa7-4657-8439-5de1f71c3df5 · outbound

This paper cites Dropmae: Masked autoen- coders with spatial-attention dropout for tracking tasks.

SAM 2++: Tracking Anything at Any Granularity Dropmae: Masked autoen- coders with spatial-attention dropout for tracking tasks

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.666114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 79c6213e-3610-4ad8-a310-8eb22d4cc691 · outbound

This paper cites Object track- ing benchmark.IEEE Transactions on Pattern Analysis and Machine Intelligence.

SAM 2++: Tracking Anything at Any Granularity Object track- ing benchmark.IEEE Transactions on Pattern Analysis and Machine Intelligence

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.682767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 735f0c76-0b3d-432a-a5f4-72dd9bb0dac8 · outbound

This paper cites Cat-sam: Con- ditional tuning for few-shot adaptation of segment anything model.

SAM 2++: Tracking Anything at Any Granularity Cat-sam: Con- ditional tuning for few-shot adaptation of segment anything model

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.676215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0042d06-6297-4269-8993-09d056fa8d71 · outbound

This paper cites YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark.

SAM 2++: Tracking Anything at Any Granularity YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-05-21T19:54:20.151923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7b18e331-2725-4a22-a273-3753a0f80ffb · outbound

This paper cites Integrating boxes and masks: A multi-object framework for unified visual tracking and segmentation.

SAM 2++: Tracking Anything at Any Granularity Integrating boxes and masks: A multi-object framework for unified visual tracking and segmentation

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.639398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 57e9ff47-420d-4be3-ae0f-3f1aef897d8e · outbound

This paper cites Learning spatio-temporal transformer for vi- sual tracking.

SAM 2++: Tracking Anything at Any Granularity Learning spatio-temporal transformer for vi- sual tracking

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.636784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e433d1eb-d7a9-4ecf-9e39-3c12d301edbc · outbound

This paper cites Towards grand unification of object tracking.

SAM 2++: Tracking Anything at Any Granularity Towards grand unification of object tracking

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.685005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c24b9cb2-9bbc-4407-ba8c-cc30b8fc987c · outbound

This paper cites Universal instance perception as object discovery and retrieval.

SAM 2++: Tracking Anything at Any Granularity Universal instance perception as object discovery and retrieval

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.631148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b9403a85-0895-4142-b313-03fa1c4e8def · outbound

This paper cites Samurai: Adapting segment anything model for zero-shot visual tracking with motion-aware memory.

SAM 2++: Tracking Anything at Any Granularity Samurai: Adapting segment anything model for zero-shot visual tracking with motion-aware memory

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.628595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c828a9af-e73e-41ea-bd9c-e4857a7ac99e · outbound

This paper cites Decoupling features in hier- archical propagation for video object segmentation.

SAM 2++: Tracking Anything at Any Granularity Decoupling features in hier- archical propagation for video object segmentation

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.625826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 13334998-2fd4-40fd-a757-60c7d6821ff8 · outbound

This paper cites Associating ob- jects with transformers for video object segmentation.

SAM 2++: Tracking Anything at Any Granularity Associating ob- jects with transformers for video object segmentation

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.623413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a65f8235-ea17-493f-abf6-4eaa956f0521 · outbound

This paper cites Joint feature learning and relation modeling for tracking: A one-stream framework.

SAM 2++: Tracking Anything at Any Granularity Joint feature learning and relation modeling for tracking: A one-stream framework

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.571974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2d686ed6-b8b4-4c04-8664-3f8819444be1 · outbound

This paper cites Unifiedtt: Visual tracking with unified transformer.

SAM 2++: Tracking Anything at Any Granularity Unifiedtt: Visual tracking with unified transformer

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.569446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fc8f4205-79f1-4bd8-9684-eb0b393349ff · outbound

This paper cites Jointformer: A unified framework with joint modeling for video object segmentation.IEEE Trans.

SAM 2++: Tracking Anything at Any Granularity Jointformer: A unified framework with joint modeling for video object segmentation.IEEE Trans

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.618081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0d04c18e-8e21-4882-919b-f59c6ea262ac · outbound

This paper cites Pointodyssey: A large-scale synthetic dataset for long-term point tracking.

SAM 2++: Tracking Anything at Any Granularity Pointodyssey: A large-scale synthetic dataset for long-term point tracking

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.615611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fef394b1-a5ce-4884-960c-65ab490885f1 · outbound

This paper cites Distance-iou loss: Faster and better learning for bounding box regression.

SAM 2++: Tracking Anything at Any Granularity Distance-iou loss: Faster and better learning for bounding box regression

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.613111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9e63aeb1-bb68-4b17-90fc-877738a17f61 · outbound

This paper cites Uni-perceiver: Pre- training unified architecture for generic perception for zero- shot and few-shot tasks.

SAM 2++: Tracking Anything at Any Granularity Uni-perceiver: Pre- training unified architecture for generic perception for zero- shot and few-shot tasks

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.588374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1d58791f-2b78-4969-95ec-ac7a3ce65b47 · outbound

This paper cites an unresolved cited work.

SAM 2++: Tracking Anything at Any Granularity Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-05-21T19:54:20.606138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a10388f8-7034-46b4-b884-29a2c4bf58f6 · outbound

This paper cites (2) Diversity: It encompasses a wide va- riety of scenes, sources, and tracked object categories, pro- viding a rich and representative sample of real-world sce- narios.

SAM 2++: Tracking Anything at Any Granularity (2) Diversity: It encompasses a wide va- riety of scenes, sources, and tracked object categories, pro- viding a rich and representative sample of real-world sce- narios

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.602684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fef78a95-a40a-44b6-9121-6cea640324be · outbound

This paper cites an unresolved cited work.

SAM 2++: Tracking Anything at Any Granularity Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-05-21T19:54:20.599779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 022e0001-e5ac-4045-ac42-6536800c5fa6 · outbound

This paper cites an unresolved cited work.

SAM 2++: Tracking Anything at Any Granularity Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-05-21T19:54:20.582129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 577add11-0bc8-483c-a7ea-817a14e81e9d · outbound

This paper cites Then, annotators refine these masks with the following re- quirements: • Only annotate the visible parts of the present object.

SAM 2++: Tracking Anything at Any Granularity Then, annotators refine these masks with the following re- quirements: • Only annotate the visible parts of the present object

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.597475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19ba0aba-75df-4e92-a573-0b9e6f750ed2 · outbound

This paper cites an unresolved cited work.

SAM 2++: Tracking Anything at Any Granularity Unresolved cited work

Reference 79

Resolution: malformed identifier; raw_fallback, observed 2026-05-21T19:54:20.595120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation adf99233-e904-4d0e-8ce2-726c0f7a145f · outbound

This paper cites Performance Comparison Evaluation metrics.Invideo object segmentationtask, we use standard metrics [47] in most benchmarks: Jaccard indexJ, contour accuracyF, and their averageJ&F.

SAM 2++: Tracking Anything at Any Granularity Performance Comparison Evaluation metrics.Invideo object segmentationtask, we use standard metrics [47] in most benchmarks: Jaccard indexJ, contour accuracyF, and their averageJ&F

Reference 80

Resolution: malformed identifier; raw_fallback, observed 2026-05-21T19:54:20.593017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 73cf8e0c-5b10-420a-9a9c-16c608e3f7f7 · outbound

This paper cites As an annotation tool, SAM 2++ supports tracking multi-granularity, which greatly re- duces the time and cost required to switch trackers between different application scenarios.

SAM 2++: Tracking Anything at Any Granularity As an annotation tool, SAM 2++ supports tracking multi-granularity, which greatly re- duces the time and cost required to switch trackers between different application scenarios

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T19:54:20.589858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers